Software & Systems

Journal articles №1 2023

1. An intelligent system for monitoring and analyzing competencies in the learning process [№1 за 2023 год]
Authors: Kulikov G. (gennadyg_98@Yahoo.com) - Ufa State Aviation Technical University (Professor), Ph.D; Antonov V.V. (antonov.v@bashkortostan.ru) - Ufa State Aviation Technical University, Faculty of IRT (Professor), Ph.D; L. Rodionova (rodionovaKF@yandex.ru) - Ufa State Aviation Technical University (Associate Professor), Ph.D; Fakhrullina A. (almirafax@mail.ru) - Ufa State Aviation Technical University (Associate Professor), Ph.D; Kromina L. (luyda-kr@yandex.ru) - Ufa State Aviation Technical University (Associate Professor), Ph.D; E.V. Palchevsky (teelxp@inbox.ru) - Financial University under the Government of the Russian Federation; Breikin T. (t.breikin@shu.ac.uk) - Sheffield Hallam University (Associate Professor), Ph.D;
Abstract: The article proposes an intelligent system (a software-analytical complex) based on an artificial neural net-work for managing the educational process based on data received from corporate business units. Modelling business process improvement involves using the Deming cycle. The paper presents a structure (model) of a software-analytical complex that makes it possible to identi-fy and trace explicitly interconnected vertical and horizontal processes, which gives a formalized description of the system that meets the algorithm requirements. There is an ontological model of the program analytics complex structure built; it is linked to a set of solutions using databases and knowledge bases; it is divided in-to classes of objects and categories with hierarchical relationships between them. In order to share this knowledge, a specific description of this data must be provided to the SAC. This description must be formal enough to be understood by another system and written in the same language. The novelty is in the consideration of a variant of solving the problem of integrating information systems associated with weakly structured subject-oriented information flows of an educational institution using the methods of set theory and category theory. The properties of relations between accounting objects are de-scribed at a high abstraction level; it becomes possible to significantly expand the scope of the proposed method for constructing a software-analytical complex based on an ontological model for various subject areas, taking into account the multi-level consideration of the subject area itself, the same consideration of finite and infinite ranges of values. At the same time, the necessary abstraction level is automatically deter-mined to ensure the structural and parametric integrity of the system being formed and the interpretation of the emerging problems of data analysis represented by semantic models.
Keywords: software analytical package, formal model, artificial neural network, deming cycle, the competence, additional professional education
Visitors: 3925

2. Cognitive regulators: soft computing technologies and the information-thermodynamic law of intelligent control self-organization [№1 за 2023 год]
Authors: Shevchenko A.A. (allabard@yandex.ru) - Dubna State University – Institute of System Analysis and Control (Postgraduate Student); Shevchenko A.V. (sh3vchenkoav@yandex.ru) - Dubna State University – Institute of System Analysis and Control (Postgraduate Student); Zrelova D.P. (zrelova@jinr.ru) - Dubna State University – Institute of System Analysis and Management, Joint Institute for Nuclear Research – Meshcheryakov Laboratory of Information Technologies (Researcher Assistant); Ulyanov, S.V. (ulyanovsv46_46@mail.ru) - Dubna State University – Institute of System Analysis and Control, Dubna, Joint Institute for Nuclear Research – Laboratory of Information Technology (Professor), Ph.D;
Abstract: The paper considers a methodology for designing intelligent cognitive control systems for complex dynamic systems. There are brief descriptions of informational and thermodynamic approaches that unite dynamic stability, controllability and robustness criteria under a homogeneous condition. The authors indicate the problems of training and adaptation of a fuzzy controller, which are relevant in modern control theory. Many existing solutions use artificial neural network models based on the backprop-agation algorithm (BP), the Cohen multilayer structure, etc. Unfortunately, such algorithms do not guarantee the required level of reliability and control accuracy in complex unforeseen situations. These schemes work successfully if the control task is performed in the absence of underdetermined stochastic noise in the envi-ronment, in sensors, in the control loop, etc. The paper proposes one of the solutions to the problem of developing a cognitive control system, which proposes a constructive solution to the problems of designing knowledge bases and intelligent robust cogni-tive control in a given problem-oriented application. There is a comparison of various types of regulators, in-cluding an intelligent regulator based on emotional brain training. The paper describes the advantages of de-signing robust knowledge bases based on the software-algorithmic complex Soft Computing Optimizer based on fuzzy logic. The paper also considers one of the key tasks of modern robotics that is the development of technologies for cognitive mechanical interaction, which makes it possible to implement intelligent control functions through the redistribution of knowledge and control at the program level. A practical example shows the ef-fectiveness of the proposed hybrid cognitive control system, which increases the accuracy and reliability of recognizing mental commands.
Keywords: knowledge base optimizer, , cognitive control system, information-thermodynamic law, intelligent controllers, soft computing
Visitors: 3972

3. Industrial robotic intelligent robust control system:  applying quantum soft computing technologies  and quantum software engineering  in unpredicted control situations [№1 за 2023 год]
Authors: Ulyanov, S.V. (ulyanovsv46_46@mail.ru) - Dubna State University – Institute of System Analysis and Control, Dubna, Joint Institute for Nuclear Research – Laboratory of Information Technology (Professor), Ph.D; A.G. Reshetnikov (reshetnikovag@pochta.ru) - Dubna State University, Institute of the System Analysis and Control (Associate Professor); Zrelova D.P. (zrelova@jinr.ru) - Dubna State University – Institute of System Analysis and Management, Joint Institute for Nuclear Research – Meshcheryakov Laboratory of Information Technologies (Researcher Assistant);
Abstract: The strategy for designing intelligent control systems based on quantum and soft computing technologies is described. The synergetic effect of quantum self-organization of a robust knowledge base, extracted from imperfect knowledge bases of an intelligent fuzzy controller, is presented. The developed technology im-proves the reliability of intelligent cognitive control systems in unforeseen control situations, for example, with various types of interacting robots. Benchmarks demonstrated the effective implementation of a quantum fuzzy inference circuit as a ready-made programmable algorithmic solution for lower-level control systems embedded in a standard board, demonstrated the quantum superiority of quantum intelligent control of classical control objects, ex-panding the Feynman-Manin thesis. The correct physical interpretation of the process of controlling self-organization at the quantum level is discussed on the basis of quantum information-thermodynamic models of exchange and extraction of quantum (hidden) valuable information from/between classical particle trajectories in the “swarm of inter-acting particles” model. A new information synergetic effect is demonstrated: a robust knowledge base of a quantum fuzzy controller is created in real time from two unreliable knowledge bases of a fuzzy controller. This effect is purely quantum in nature and uses hidden quantum information extracted from classical states. The main physical and information-thermodynamic aspects of the model of quantum intelligent con-trol of classical control objects are discussed.
Keywords: industrial robot, quantum algorithms, robustness, intelligent control in unpredicted situations, quantum fuzzy inference
Visitors: 4011

4. Modeling the intelligent agent behavior based on machine learning methods in competition models [№1 за 2023 год]
Authors: A.O. Anokhin (alex.anokhin.st@gmail.com) - Volgograd State Technical University (Postgraduate Student); D.S. Parygin (dparygin@gmail.com) - Volgograd State Technical University (Associate Professor), Ph.D; Sadovnikova, N.P. (npsn1@ya.ru) - Volgograd State Technical University (Professor), Ph.D; Finogeev A.A. (fanton3@ya.ru) - Penza State University (Associate Professor), Ph.D; Gurtyakov A.S. (agurtyakov@gmail.com) - Volgograd State Technical University (Associate Professor), Ph.D;
Abstract: The article discusses the aspects of applying machine learning methods to existing methods for modeling the behavior of intelligent agents to enable agents to improve their performance in competition models. The practical significance of the study is represented by developing an approach to modeling the behav-ior of intelligent agents in order to increase the efficiency of their functioning in such areas as computer games, developing unmanned aerial vehicles and search robots, studying urban and transport mobility, as well as other complex systems. There is a review of the existing machine learning methods (reinforcement learning, deep learning, Q-learning) and methods for modeling the agents’ behavior (a rule-based model, a finite automaton model of behavior, behavior trees). The authors have chosen the most appropriate combination of a learning method and a behavior model for the task: behavior trees and reinforcement learning. A test platform was implemented using Unity tools, behavior models were developed for the four main archetypes of agents that must compete in collecting resources in a limited time. A trained agent was imple-mented using Unity ML and TensorFlow tools. The test platform has become a basis for a series of experiments under various conditions: limited re-sources, resource abundance, average amount of resources. As part of the experiment, the authors tested the ability of the developed intelligent agent’s behavior model to win in a competitive environment with agents equipped with various variants of traditional behavior models based on behavior trees. The efficiency and advantages of using the developed behavior model were evaluated. The paper analyzes the experimental re-sults and draws conclusions regarding the potential of the selected combination of methods.
Keywords: behavior tree, machine learning, artificial intelligence, intelligent agent, behavior modeling
Visitors: 4370

5. An IT system for assessing the impact of energy objects on environment [№1 за 2023 год]
Authors: Kuzmin V.R. (rulisp@vigo.su) - Melentiev Energy Systems Institute SB RAS (Junior Researcher); L.V. Massel (massel@isem.irk.ru) - Melentiev Energy Systems Institute SB RAS (Professor, Head of the Department of Artificial Intelligence Systems in the Energy Sector), Ph.D;
Abstract: The subject of the article is the author's information and computer system called WICS for assessing the im-pact of energy facilities on the environment. The paper substantiates the necessity of both performing such assessments and developing an appropriate system. When building an information and computer system, the authors used the following methods: methods for building client-server Web applications to optimize the requirements for users' computers and to organize teamwork; methods for constructing multi-agent systems for optimizing calculations. In order to implement the database, the authors applied ontological engineering of subject areas that are energy and ecology. The article shows the architecture of the developed system, describes the developed information subsystems based on approved normative methods for performing calculations. Empirical Bayesian kriging is used to in-terpolate the results of the analysis of snow tests for pollutants. There are the results of approbating the de-veloped system on the example of data on the Central Ecological Zone of the Baikal Natural Territory. The proposed system can be used both for assessing the current situation with environmental pollution by energy objects, and when planning measures to reduce their harmful effects or installation of new gener-ating capacities.
Keywords: impact assessment, ontological engineering, information-computer system, environment, energy objects
Visitors: 3400

6. Developing and modeling a hybrid dynamic routing protocol [№1 за 2023 год]
Authors: L.I. Abrosimov (AbrosimovLI@mpei.ru) - National Research University “Moscow Power Engineering Institute” (Professor), Ph.D; H. Khayou (hussein.khayou@gmail.com) - National Research University “Moscow Power Engineering Institute” (Postgraduate Student); M.A. Orlova (OrlovaMA@mpei.ru) - National Research University “Moscow Power Engineering Institute” (Assistant);
Abstract: Nowadays, the growth of network services significantly increases the requirements for the quality and speed of solving network management problems in ever-growing data centers. The load increase in data centers leads to the need for structural scaling that implies increasing the number of servers and routers. There is a need for simple scalable routing protocols to facilitate automation and management of ever-growing net-works, especially in data centers. The work aims to present and simulate a new hybrid dynamic routing protocol including an upgraded dis-tance vector routing algorithm and a link state algorithm. The article discusses the solution to the problems of developing a hybrid dynamic routing protocol, which guarantees loop freedom and provides scaling requirements through the development and implementation of simple algorithms that ensure reliable transmission of data and service traffic containing route infor-mation and detects channels, networks, and directly connected neighboring routers connected to the current router. The scalability requirements of the new hybrid dynamic routing protocol are met since the distance vector routing algorithm calculates the distances to infrastructure nodes, and not to the network prefixes themselves. The link state algorithm advertises network prefixes only once, which leads to a reduction in the link state database and a reduction in calculations after topology changes. Loop freedom is achieved by in-troducing a newly developed distributed sequence number algorithm. A simulation model has been developed to simulate the hybrid dynamic routing protocol. The simulation allowed estimating the amount and volume of service traffic, which confirmed the effectiveness of the de-veloped protocol in the conditions of scaling the data center network.
Keywords: dynamic routing hybrid protocol, algorithm, mathematical model, loopless routing, routing protocol scalability
Visitors: 3973

7. Integrating the subject area subspace into the “mathematics” semantic space [№1 за 2023 год]
Authors: Ataeva O.M. (oli@ultimeta.ru) - A.A. Dorodnitsyn Computing Centre of RAS (Junior Researcher); Serebryakov V.A. (serebr@ultimeta.ru) - A.A. Dorodnitsyn Computing Centre of RAS (Professor, Head of Department), Ph.D; Tuchkova N.P. (natalia_tuchkova@mail.ru) - Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences (FRC CSC RAS) (Senior Researcher), Ph.D;
Abstract: The paper studies the problem of developing a semantic library by adding a new applied scientific area. The authors use the example of a journal on applied issues of composite materials in order to build an addition to the main content of the library, to expand the description of the original subject area, and to detail UDC and MSC articles corresponding to the local subject area. At the same time, they solve the tasks of adding terms to the thesaurus, building a reference corpus of the applied subject area of mathematics, and creating a custom interface. Formulas and equations of the local subject area are semantically linked to the main content of the library. The main advantage of using semantic libraries for this kind of tasks is to enrich the existing knowledge base of the library and identify relationships in data. To study these problems, it is necessary to interact with subject matter experts and use modern tools and methods for natural language processing, machine learning approaches to knowledge representation. The above tasks are implemented by means of the LibMeta se-mantic library, which allows considering such concepts as the thematic area/subdomain and their hierar-chical relationships, in particular, the automatic inclusion of the enclosing area concepts in the subdomain knowledge system; the possibility of personalizing the built structures and using LibMeta as a construction tool, in particular, building the ontology itself. Data integration within the library allows expanding the de-scription of subject areas related to the applications of mathematics in interdisciplinary research and tech-nology. As an example of one of the applied sections of mathematical physics problems, the procedure for including specific dictionaries, thesauri, as well as an array of publications of a specialized journal in a se-mantic library is shown. The proposed approach will allow using the content of the “mathematics” semantic library for scientific research and minimizing the process of searching for information in the local subject ar-ea, without losing more general results contained outside this area.
Keywords: local subject domain search, local thesaurus, domain ontology, applied ontology, semantic library
Visitors: 4322

8. Developing a software tool for constructing a social graph of a social network user in the task of analyzing its security from multi-pass social engineering attacks [№1 за 2023 год]
Authors: Khlobystova, A.O. (aok@dscs.pro) - St. Petersburg Federal Research Center of the Russian Academy of Sciences, Laboratory of Theoretical and Interdisciplinary Problems of Informatics (Junior Researcher); Abramov, M.V. (mva@dscs.pro) - St. Petersburg Federal Research Center of the Russian Academy of Sciences, Laboratory of Theoretical and Interdisciplinary Problems of Informatics (Head of Laboratory), Ph.D; Sazanov, V.A. (mail@dscs.pro) - St. Petersburg State University (Student);
Abstract: The study is based on the problem of lacking visualization tools showing the intensity of interaction between users of the VK online social network, namely the display of metrics that allow evaluating and ranking the intensity of interaction both between a user and his friends, and between friends with each other. The aim of this paper is to improve the accessibility and timeliness of users’ interaction intensity analysis by automating social graph visualization. It is assumed that the numerical coefficients of the social graph arcs will be compared with an assessment of user interaction intensity based on data extracted from publicly available sources of the VK social network. To achieve this goal, the authors considered the following issues: optimization of aggregating necessary data on observed interaction of friends in the VK social network, software implementation of functions for building a social graph, visualization of users' interaction intensity with the possibility of choosing metrics of interest, creation of convenient interface and embedding the developed toolkit into a web-application. The subject of the research is the data of interaction between VK users and the ways of their visualiza-tion. The research methods are based on optimizing sending queries to VK API, as well as developing func-tions and settings to build a social graph. The theoretical significance of the proposed solution is in the development of approaches to analyze the proliferation of multistep social engineering attacks and to validate models for estimating user interaction in-tensity. The result has significant practical relevance consisting in automating the process of assessing the in-tensity of employee interaction, thereby laying the foundation for taking effective measures to mitigate the risks of successful social engineering attacks. The novelty of the research is in the proposed improvement of visualization of VK users' social graph construction by adding new metrics to assess the intensity of users' in-teraction.
Keywords: web application architecture for building the social graph, user interaction intensity metrics, infosecurity, web application, social networks, interaction visualization, spread probability estimate, social engineering attacks, social graph
Visitors: 4189

9. An algorithm for using distributed computing resources based on the Edge computing principles [№1 за 2023 год]
Authors: Vorobev A.M. (a.m.vorobev@utmn.ru) - University of Tyumen (Senior Lecturer); Vorobeva M.S. (m.s.vorobeva@utmn.ru) - University of Tyumen (Associate Professor), Ph.D; Boganyuk Yu.V. (y.v.boganyuk@utmn.ru) - University of Tyumen (Postgraduate Student);
Abstract: The article describes the issues of implementing the algorithm for distributing computational tasks over a set of distributed computing resources with subsequent aggregation of the results. This algorithm is the key one in the framework of the data center implementation project based on the sharing economy principles. The mechanism prototype is implemented in Python 3.8 using the PostgreSQL 14 DBMS, the message passing system is implemented on the basis of RabbitMQ 3.9, the computing node platform is CentOS 8 Stream OS. The purpose of the work is to implement a scalable distributed computing mechanism for using as the main instrument of task distribution and aggregation of results within the framework of the data center con-cept based on the sharing economy principles. The subject of the study is the methods of computing power redundancy and use, aggregation of the working results of software algorithms. The proposed mechanism solves the computing distribution problem with subsequent aggregation of re-sults among computing nodes with different technical characteristics. There is an implemented interface suitable for integrating into client information systems as a means of uploading calculations with access in the REST API gateway format. The theoretical significance of the work is in combining the existing principles and ideas of Edge compu-ting to solve a different class of problems, where the problem is the lack of a computing resource for infor-mation system tasks, and not insufficient characteristics of the existing model. The practical significance is in the development of an application tool for using external computing pow-er to solve a wide class of client tasks, which gives the possibility of organizing commercial interaction be-tween owners of unused computing resources and owners of information systems that lack computing pow-er.
Keywords: calculation offload, rest api, virtual machine, asynchronous calls, amqp, messaging bus, distributed computing
Visitors: 3504

10. A simulation model of distributed object radar tracking [№1 за 2023 год]
Authors: D.V. Khrestinin (diiimaaarik@mail.ru) - A.F. Mozhaysky Military Space Academy (Lecturer); Pozdnyakov A.A. (vka@mil.ru) - A.F. Mozhaysky Military Space Academy (Senior Lecture), Ph.D;
Abstract: The subject of research is radar tracking of distributed objects like groups of small drones. The peculiarity of these objects is in their complex composition and an unusual for most classic aircrafts movement character. The research method is simulation modeling. It allows evaluating the effectiveness of radar tracking algorithms and classification in selected terms. The article presents the process organization of simulation modeling of integrated radar system functioning in the de-tection, measurement, tracking and classification modes. It also presents the description of analytical models and their inter-action, as well as simulation results, which are received using traditional experiment processing methods. The methods take into account a required number of tests to provide probability values in confidence interval no more than 0,01 of the ob-tained value with a confidence probability no more than 0.8. The authors evaluated performance of the most popular tracking and classification algorithms. Tracking algorithms include α-β-γ algorithm, Kalman filter, Unscented Kalman filter, partial filter. Classification algorithms include optimal Bayes algorithm, parting algorithm, Viterbi algorithm, Savrasov algorithm. The model, unlike the known ones, takes into account the influence of all reflections and re-reflections of the probing signal from the sophisticated object elements. According to the simulation results, the authors make a conclusion that among the tracking algorithms, the most effi-cient are algorithms based on the partial filter and Unscented Kalman filter; among the classification algorithms, the most ef-ficient is Savrasov algorithm. However, based on the requirements for a radar performance, none of the considered algo-rithms provides the required quality under the described conditions. This indicates the need to improve the scientific and methodological apparatus of radar trajectory processing.
Keywords: distributed observation objects, radar tracking, radar simulation
Visitors: 2910

| 1 | 2 | Next → ►